---

language: en

license: apache-2.0

base_model: unsloth/Qwen2.5-1.5B-Instruct

datasets:

• r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation

tags:

• qwen2.5
• tool-calling
• function-calling
• agents
• distillation
• kimi-k3
• lora
• gguf

library_name: gguf

---

Qwen2.5-1.5B k3 GGUF

The Qwen2.5-1.5B k3 tool-calling model in GGUF format, fine-tuned

with LoRA on Kimi-K3 distillation data.

Base model

This model was fine-tuned from:

unsloth/Qwen2.5-1.5B-Instruct

GGUF files

The model is provided in GGUF format at the following precisions:

| Precision | File |

|---|---|

| BF16 | Qwen2.5-1.5B-k3-BF16.gguf (original precision) |

| Q4_K_M | Qwen2.5-1.5B-k3-Q4_K_M.gguf |

Training

Training was performed using NVIDIA NeMo AutoModel with LoRA/PEFT.

LoRA configuration

• LoRA dimension: 16
• LoRA alpha: 16
• Dropout: 0.05
• Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Training configuration

• Max sequence length: 4096
• Learning rate: 2e-5
• Weight decay: 0.01
• Global batch size: 4 (micro batch 1 x 4 accumulation)
• Epochs: 1
• Mixed precision: bf16

Dataset

Training used the sft_balanced split of the

r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation dataset.

Intended use

• Structured tool/function calling
• Agent-style multi-step interactions
• Distilled reasoning behavior from the Kimi-K3 data mix

It is not intended to be a general replacement for larger Qwen models.

GGUF versions

The model is available in GGUF format at:

• BF16
• Q4_K_M

More precisions can be quantized locally from the BF16 file with

llama-quantize.

Usage

Run the model with llama.cpp:

llama-cli -hf iromu/Qwen2.5-1.5B-k3-GGUF:Q4_K_M

<!-- VALIDATION:BEGIN (auto-generated, do not edit) -->

Validation matrix

Tool-calling validation on the sft_tools validation split (greedy decoding, 384 max new tokens). Throughput is single-stream greedy decode, not serving throughput.

Pretrained base (unsloth/Qwen2.5-1.5B-Instruct): 8.0% exact-args match (4/50).

Fine-tuned (BF16): 0.7% exact-args match (2/274) (-7.3pp vs base).

• GGUF-BF16: 5/274 (1.8%) exact, 89.5 tok/s — 250% of BF16.
• GGUF-Q4_K_M: 7/274 (2.6%) exact, 128.6 tok/s — 350% of BF16.

| Model | Quant | n | Tool call emitted | Names match | Exact args match | Δ exact vs BASE | tok/s |

|---|---|---|---|---|---|---|---|

| Qwen2.5-1.5B-k3 | BASE (unsloth/Qwen2.5-1.5B-Instruct) | 50 | 50/50 (100.0%) | 13/50 (26.0%) | 4/50 (8.0%) | — | 39.2 |

| Qwen2.5-1.5B-k3 | BF16 | 274 | 254/274 (92.7%) | 170/274 (62.0%) | 2/274 (0.7%) | -7.3pp | 41.2 |

| Qwen2.5-1.5B-k3 | GGUF-BF16 | 274 | 271/274 (98.9%) | 157/274 (57.3%) | 5/274 (1.8%) | -6.2pp | 89.5 |

| Qwen2.5-1.5B-k3 | GGUF-Q4_K_M | 274 | 264/274 (96.4%) | 103/274 (37.6%) | 7/274 (2.6%) | -5.4pp | 128.6 |

<!-- VALIDATION:END -->